Downloads · 30 days
4
21% of all-time downloads
BarryFutureman_-_WestLakeX-7B-EvoMerge-8bits
RichardErkhov/BarryFutureman_-_WestLakeX-7B-EvoMerge-8bits
BarryFutureman_-_WestLakeX-7B-EvoMerge-8bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
19
Public
Parameters
7.2B
7.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.5 GB · 100%
Parameter types
How the weights are stored.
I87B · 96%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
WestLakeX-7B-EvoMerge - bnb 8bits
- Model creator: https://huggingface.co/BarryFutureman/
- Original model: https://huggingface.co/BarryFutureman/WestLakeX-7B-EvoMerge/
Original model description:
base_model: [] license: apache-2.0 datasets:
- argilla/distilabel-intel-orca-dpo-pairs
WestLakeX-7B-EvoMerge
This is the result of a small-scale EvoMerge.
(Experiment Conclusion: Higher mutation strength does not seem to improve performance so far. Average eval score is below all candidates in initial population. Though this is a single experiment, it is not definitive that higher mutation strength is unnecessary. For example, it could be useful at a bigger scale.)
Zoom in to view the family tree:
- Type
- mistral
- Created
- Aug 29, 2024
- Updated
- Aug 29, 2024